Update app.py

app.py

@@ -5,6 +5,7 @@ import soundfile as sf
 import numpy as np
 import torch  # Import torch
 from espnet2.bin.tts_inference import Text2Speech
+import spaces
 
 # --- Whisper (ASR) - We'll use this instead of image captioning ---
 ASR_MODEL_NAME = "openai/whisper-large-v2"